Development and Validation of a Machine Learning Approach for Automated Severity Assessment of COVID-19 Based on Clinical and Imaging Data: Retrospective Study.

BACKGROUND: COVID-19 has overwhelmed health systems worldwide. It is important to identify severe cases as early as possible, such that resources can be mobilized and treatment can be escalated. OBJECTIVE: This study aims to develop a machine learning approach for automated severity assessment of COVID-19 based on clinical and imaging data. METHODS: Clinical data-including demographics, signs, symptoms, comorbidities, and blood test results-and chest computed tomography scans of 346 patients from 2 hospitals in the Hubei Province, China, were used to develop machine learning models for automated severity assessment in diagnosed COVID-19 cases. We compared the predictive power of the clinical and imaging data from multiple machine learning models and further explored the use of four oversampling methods to address the imbalanced classification issue. Features with the highest predictive power were identified using the Shapley Additive Explanations framework. RESULTS: Imaging features had the strongest impact on the model output, while a combination of clinical and imaging features yielded the best performance overall. The identified predictive features were consistent with those reported previously. Although oversampling yielded mixed results, it achieved the best model performance in our study. Logistic regression models differentiating between mild and severe cases achieved the best performance for clinical features (area under the curve [AUC] 0.848; sensitivity 0.455; specificity 0.906), imaging features (AUC 0.926; sensitivity 0.818; specificity 0.901), and a combination of clinical and imaging features (AUC 0.950; sensitivity 0.764; specificity 0.919). The synthetic minority oversampling method further improved the performance of the model using combined features (AUC 0.960; sensitivity 0.845; specificity 0.929). CONCLUSIONS: Clinical and imaging features can be used for automated severity assessment of COVID-19 and can potentially help triage patients with COVID-19 and prioritize care delivery to those at a higher risk of severe disease.

Combined application of DTI and BOLD-MRI in the assessment of renal injury with hyperuricemia.

OBJECTIVE: To explore the value of combined diffusion tensor imaging (DTI) and blood oxygenation level-dependent magnetic resonance imaging (BOLD-MRI) in detecting early renal alterations in patients with hyperuricemia. MATERIALS AND METHODS: Seventy-one individuals were enrolled in this study and divided into three groups according to their serum uric acid (SUA) level and clinical symptoms: healthy controls (HC, n = 23), asymptomatic hyperuricemia (AH, n = 22) and gouty arthritis (GA, n = 26). All patients underwent both DTI and BOLD-MRI examination. Renal cortical and medullary ADC, FA and R2* values were calculated, respectively, and compared among the three groups. Correlations between ADC, FA and R2* with estimated glomerular filtration rate (eGFR) and SUA in hyperuricemia were evaluated, respectively. RESULT: In the renal cortex, the ADC, FA and R2* values of the AH and GA groups were significantly lower than those of the HC groups (p < 0.05). In the renal medulla, the ADC and FA values in AH and GA patients were significantly lower than those in healthy controls (p < 0.05). The R2* value of the GA group significantly decreased, compared to that of the AH and HC groups (p < 0.05). SUA was negatively correlated with cortical ADC, FA and R2* values (p < 0.05) as well as with medullary ADC and FA values. No significant correlation was discovered between the eGFR and ADC, FA and R2* values. CONCLUSION: The combined evaluation of DTI and BOLD might provide a sensitive and non-invasive approach for detection of renal microstructural alterations and oxygen metabolism abnormality in hyperuricemia.